Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    document_ access patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     metastatic
    0.38
    ジナル
    0.37
    ᵘ
    0.37
     দশমিক
    0.36
    ()=>{
    0.36
    estellt
    0.33
     গতি
    0.33
    olidated
    0.33
    ğunu
    0.33
    iooni
    0.33
    POSITIVE LOGITS
    in
    0.33
    if
    0.32
    first
    0.31
    awt
    0.31
    name
    0.31
    desc
    0.30
    is
    0.29
    arre
    0.29
     We
    0.29
    Watch
    0.28
    Act Density 0.001%

    No Known Activations